Machine Learning Portfolio Risk and Returns

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import math

import warnings
warnings.filterwarnings("ignore")

# fix_yahoo_finance is used to fetch data 
import fix_yahoo_finance as yf
yf.pdr_override()

# input
# Machine Learning Stock
symbols = ['GOOGL','MSFT','FB','AMZN','NFLX','CRM','ADBE','MTCH','IAC','TTD','FIVN','V','MA','PANW','IBM','FTNT','NVDA','INTC','CUB','IBM','ACN','EPAM']
start = '2017-01-01'
end = '2019-01-01'

df = pd.DataFrame()
for s in symbols:
    df[s] = yf.download(s,start,end)['Adj Close']

[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded
[*********************100%***********************]  1 of 1 downloaded

from datetime import datetime
from dateutil import relativedelta

d1 = datetime.strptime(start, "%Y-%m-%d")
d2 = datetime.strptime(end, "%Y-%m-%d")
delta = relativedelta.relativedelta(d2,d1)
print('How many years of investing?')
print('%s years' % delta.years)

How many years of investing?
2 years

number_of_years = delta.years

days = (df.index[-1] - df.index[0]).days
days

727

df.head()

	GOOGL	MSFT	FB	AMZN	NFLX	CRM	ADBE	MTCH	IAC	TTD	...	V	MA	PANW	IBM	FTNT	NVDA	INTC	CUB	ACN	EPAM
Date
2017-01-03	808.010010	59.294807	116.860001	753.669983	127.489998	70.540001	103.480003	16.494013	67.440002	26.930000	...	77.918709	103.471863	126.940002	146.935089	30.120001	100.937172	33.873764	48.126457	110.738106	63.660000
2017-01-04	807.770020	59.029503	118.690002	757.179993	129.410004	72.800003	104.139999	16.455944	68.169998	27.100000	...	78.555786	104.453651	128.000000	148.754303	30.420000	103.292122	33.697922	49.556442	111.004356	64.360001
2017-01-05	813.020020	59.029503	120.669998	780.450012	131.809998	72.790001	105.910004	17.122175	69.349998	27.450001	...	79.477066	105.260406	131.970001	148.262131	30.830000	100.670013	33.642395	47.140259	109.340340	64.750000
2017-01-06	825.210022	59.541157	123.410004	795.989990	131.070007	73.800003	108.300003	17.160246	69.650002	27.700001	...	80.574791	106.017982	135.050003	148.991577	31.010000	102.015701	33.762699	46.203373	110.585968	66.870003
2017-01-09	827.179993	59.351658	124.900002	796.919983	130.949997	73.959999	108.570000	17.274456	69.779999	28.440001	...	80.123962	105.811363	133.720001	147.339340	31.309999	106.151749	33.883030	46.104755	109.349854	66.839996

5 rows × 21 columns

plt.figure(figsize=(12,8))
plt.plot(df)
plt.title('Machine Learning Stocks Closing Price')
plt.legend(labels=df.columns)

<matplotlib.legend.Legend at 0x1dc4f915550>

# Normalize the data
normalize = (df - df.min())/ (df.max() - df.min())

plt.figure(figsize=(18,12))
plt.plot(normalize)
plt.title('Machine Learning Stocks Normalize')
plt.legend(labels=normalize.columns)

<matplotlib.legend.Legend at 0x1dc4f9b3b70>

stock_rets = df.pct_change().dropna()

plt.figure(figsize=(12,8))
plt.plot(stock_rets)
plt.title('Machine Learning Stocks Returns')
plt.legend(labels=stock_rets.columns)

<matplotlib.legend.Legend at 0x1dc4fa4dfd0>

plt.figure(figsize=(12,8))
plt.plot(stock_rets.cumsum())
plt.title('Machine Learning Stocks Returns Cumulative Sum')
plt.legend(labels=stock_rets.columns)

<matplotlib.legend.Legend at 0x1dc4fae8898>

sns.set(style='ticks')
ax = sns.pairplot(stock_rets, diag_kind='hist')

nplot = len(stock_rets.columns)
for i in range(nplot) :
    for j in range(nplot) :
        ax.axes[i, j].locator_params(axis='x', nbins=6, tight=True)

ax = sns.PairGrid(stock_rets)
ax.map_upper(plt.scatter, color='purple')
ax.map_lower(sns.kdeplot, color='blue')
ax.map_diag(plt.hist, bins=30)
for i in range(nplot) :
    for j in range(nplot) :
        ax.axes[i, j].locator_params(axis='x', nbins=6, tight=True)

plt.figure(figsize=(7,7))
corr = stock_rets.corr()

# plot the heatmap
sns.heatmap(corr, 
        xticklabels=corr.columns,
        yticklabels=corr.columns,
            cmap="Blues")

<matplotlib.axes._subplots.AxesSubplot at 0x1dc61ee4518>

# Box plot
stock_rets.plot(kind='box',figsize=(12,8))

<matplotlib.axes._subplots.AxesSubplot at 0x1dc5d13fcc0>

rets = stock_rets.dropna()

plt.figure(figsize=(12,8))
plt.scatter(rets.mean(), rets.std(),alpha = 0.5)

plt.title('Stocks Risk & Returns')
plt.xlabel('Expected returns')
plt.ylabel('Risk')
plt.grid(which='major')

for label, x, y in zip(rets.columns, rets.mean(), rets.std()):
    plt.annotate(
        label, 
        xy = (x, y), xytext = (50, 50),
        textcoords = 'offset points', ha = 'right', va = 'bottom',
        arrowprops = dict(arrowstyle = '-', connectionstyle = 'arc3,rad=-0.3'))

rets = stock_rets.dropna()
area = np.pi*20.0

sns.set(style='darkgrid')
plt.figure(figsize=(12,8))
plt.scatter(rets.mean(), rets.std(), s=area)
plt.xlabel("Expected Return", fontsize=15)
plt.ylabel("Risk", fontsize=15)
plt.title("Return vs. Risk for Stocks", fontsize=20)

for label, x, y in zip(rets.columns, rets.mean(), rets.std()) : 
    plt.annotate(label, xy=(x,y), xytext=(50, 0), textcoords='offset points',
                arrowprops=dict(arrowstyle='-', connectionstyle='bar,angle=180,fraction=-0.2'),
                bbox=dict(boxstyle="round", fc="w"))

rest_rets = rets.corr()
pair_value = rest_rets.abs().unstack()
pair_value.sort_values(ascending = False)

EPAM   EPAM     1.000000
TTD    TTD      1.000000
INTC   INTC     1.000000
NVDA   NVDA     1.000000
FTNT   FTNT     1.000000
IBM    IBM      1.000000
PANW   PANW     1.000000
MA     MA       1.000000
V      V        1.000000
IAC    IAC      1.000000
ACN    ACN      1.000000
MTCH   MTCH     1.000000
ADBE   ADBE     1.000000
CRM    CRM      1.000000
NFLX   NFLX     1.000000
AMZN   AMZN     1.000000
FB     FB       1.000000
MSFT   MSFT     1.000000
CUB    CUB      1.000000
FIVN   FIVN     1.000000
GOOGL  GOOGL    1.000000
MA     V        0.892900
V      MA       0.892900
MTCH   IAC      0.786228
IAC    MTCH     0.786228
CRM    ADBE     0.785597
ADBE   CRM      0.785597
CRM    MA       0.781389
MA     CRM      0.781389
MSFT   V        0.777083
                  ...   
TTD    FIVN     0.245916
FIVN   TTD      0.245916
CUB    IBM      0.245631
IBM    CUB      0.245631
FIVN   CUB      0.244070
CUB    FIVN     0.244070
TTD    NVDA     0.230372
NVDA   TTD      0.230372
CUB    FB       0.220368
FB     CUB      0.220368
IBM    IAC      0.217917
IAC    IBM      0.217917
PANW   TTD      0.210500
TTD    PANW     0.210500
MTCH   FIVN     0.210139
FIVN   MTCH     0.210139
CUB    PANW     0.208563
PANW   CUB      0.208563
INTC   TTD      0.205115
TTD    INTC     0.205115
IBM    PANW     0.197830
PANW   IBM      0.197830
CUB    TTD      0.190216
TTD    CUB      0.190216
MTCH   IBM      0.165667
IBM    MTCH     0.165667
       FIVN     0.161164
FIVN   IBM      0.161164
TTD    IBM      0.159211
IBM    TTD      0.159211
Length: 441, dtype: float64

# Normalized Returns Data
Normalized_Value = ((rets[:] - rets[:].min()) /(rets[:].max() - rets[:].min()))
Normalized_Value.head()

	GOOGL	MSFT	FB	AMZN	NFLX	CRM	ADBE	MTCH	IAC	TTD	...	V	MA	PANW	IBM	FTNT	NVDA	INTC	CUB	ACN	EPAM
Date
2017-01-04	0.448891	0.383439	0.732522	0.393867	0.475429	0.627588	0.427781	0.555197	0.587599	0.254630	...	0.478502	0.553318	0.604241	0.537590	0.520225	0.576488	0.421603	0.582652	0.570820	0.434195
2017-01-05	0.506997	0.417845	0.736170	0.517822	0.490618	0.458039	0.480143	0.663876	0.607814	0.266139	...	0.508544	0.539717	0.659046	0.442458	0.533028	0.443317	0.440115	0.273118	0.438834	0.400648
2017-01-06	0.579618	0.484498	0.757669	0.466382	0.385336	0.531879	0.507609	0.566706	0.567343	0.259501	...	0.526173	0.535660	0.640483	0.492351	0.505226	0.549251	0.467406	0.387046	0.639017	0.581980
2017-01-09	0.471840	0.393372	0.719724	0.377282	0.405810	0.470187	0.408624	0.577961	0.559677	0.290194	...	0.362010	0.465174	0.560236	0.395281	0.519185	0.623540	0.467344	0.457025	0.467764	0.356416
2017-01-10	0.439338	0.415390	0.660924	0.365643	0.374526	0.460188	0.382250	0.579249	0.559666	0.269369	...	0.363812	0.463713	0.601409	0.385485	0.559529	0.492071	0.438734	0.532946	0.556535	0.370650

5 rows × 21 columns

Normalized_Value.corr()

	GOOGL	MSFT	FB	AMZN	NFLX	CRM	ADBE	MTCH	IAC	TTD	...	V	MA	PANW	IBM	FTNT	NVDA	INTC	CUB	ACN	EPAM
GOOGL	1.000000	0.771586	0.640550	0.719742	0.602570	0.699130	0.675725	0.368385	0.431154	0.319827	...	0.737875	0.714641	0.364781	0.425271	0.484578	0.559668	0.533903	0.332338	0.588746	0.571456
MSFT	0.771586	1.000000	0.547119	0.738228	0.609286	0.752413	0.770251	0.354319	0.411753	0.337338	...	0.777083	0.773570	0.375190	0.459310	0.529380	0.529161	0.605375	0.365568	0.667848	0.572117
FB	0.640550	0.547119	1.000000	0.590811	0.486307	0.522392	0.493976	0.342744	0.372240	0.289511	...	0.557580	0.584230	0.284690	0.254803	0.362659	0.472328	0.406506	0.220368	0.383739	0.394378
AMZN	0.719742	0.738228	0.590811	1.000000	0.644157	0.690820	0.648191	0.364880	0.431046	0.355095	...	0.672126	0.709773	0.366557	0.341746	0.426744	0.523415	0.481682	0.263359	0.526520	0.536802
NFLX	0.602570	0.609286	0.486307	0.644157	1.000000	0.628014	0.590377	0.383384	0.417863	0.291443	...	0.617772	0.607967	0.406267	0.323364	0.466309	0.498667	0.454671	0.265071	0.457673	0.496877
CRM	0.699130	0.752413	0.522392	0.690820	0.628014	1.000000	0.785597	0.440203	0.502546	0.366959	...	0.771157	0.781389	0.437981	0.386509	0.583155	0.549895	0.481022	0.346299	0.569139	0.589638
ADBE	0.675725	0.770251	0.493976	0.648191	0.590377	0.785597	1.000000	0.397581	0.452810	0.358018	...	0.743943	0.718496	0.400318	0.393894	0.557200	0.534651	0.469750	0.332117	0.556661	0.582843
MTCH	0.368385	0.354319	0.342744	0.364880	0.383384	0.440203	0.397581	1.000000	0.786228	0.289128	...	0.397208	0.379119	0.270165	0.165667	0.372520	0.336972	0.282441	0.267054	0.275456	0.346317
IAC	0.431154	0.411753	0.372240	0.431046	0.417863	0.502546	0.452810	0.786228	1.000000	0.387182	...	0.473497	0.455092	0.326356	0.217917	0.421267	0.370356	0.309624	0.285079	0.339965	0.389252
TTD	0.319827	0.337338	0.289511	0.355095	0.291443	0.366959	0.358018	0.289128	0.387182	1.000000	...	0.359367	0.359957	0.210500	0.159211	0.298966	0.230372	0.205115	0.190216	0.278909	0.326512
FIVN	0.433943	0.445142	0.296260	0.406407	0.381199	0.489272	0.462129	0.210139	0.279335	0.245916	...	0.434688	0.472931	0.262595	0.161164	0.370785	0.365666	0.309627	0.244070	0.330560	0.432436
V	0.737875	0.777083	0.557580	0.672126	0.617772	0.771157	0.743943	0.397208	0.473497	0.359367	...	1.000000	0.892900	0.423170	0.462394	0.569341	0.541747	0.515151	0.382200	0.651217	0.612359
MA	0.714641	0.773570	0.584230	0.709773	0.607967	0.781389	0.718496	0.379119	0.455092	0.359957	...	0.892900	1.000000	0.404769	0.448107	0.544509	0.545350	0.520801	0.379033	0.655655	0.588460
PANW	0.364781	0.375190	0.284690	0.366557	0.406267	0.437981	0.400318	0.270165	0.326356	0.210500	...	0.423170	0.404769	1.000000	0.197830	0.460549	0.296546	0.293506	0.208563	0.278169	0.358673
IBM	0.425271	0.459310	0.254803	0.341746	0.323364	0.386509	0.393894	0.165667	0.217917	0.159211	...	0.462394	0.448107	0.197830	1.000000	0.304057	0.276994	0.382657	0.245631	0.474890	0.355813
FTNT	0.484578	0.529380	0.362659	0.426744	0.466309	0.583155	0.557200	0.372520	0.421267	0.298966	...	0.569341	0.544509	0.460549	0.304057	1.000000	0.433000	0.378521	0.302912	0.419296	0.419359
NVDA	0.559668	0.529161	0.472328	0.523415	0.498667	0.549895	0.534651	0.336972	0.370356	0.230372	...	0.541747	0.545350	0.296546	0.276994	0.433000	1.000000	0.453898	0.276076	0.420250	0.424380
INTC	0.533903	0.605375	0.406506	0.481682	0.454671	0.481022	0.469750	0.282441	0.309624	0.205115	...	0.515151	0.520801	0.293506	0.382657	0.378521	0.453898	1.000000	0.305463	0.493593	0.417215
CUB	0.332338	0.365568	0.220368	0.263359	0.265071	0.346299	0.332117	0.267054	0.285079	0.190216	...	0.382200	0.379033	0.208563	0.245631	0.302912	0.276076	0.305463	1.000000	0.360593	0.335412
ACN	0.588746	0.667848	0.383739	0.526520	0.457673	0.569139	0.556661	0.275456	0.339965	0.278909	...	0.651217	0.655655	0.278169	0.474890	0.419296	0.420250	0.493593	0.360593	1.000000	0.571060
EPAM	0.571456	0.572117	0.394378	0.536802	0.496877	0.589638	0.582843	0.346317	0.389252	0.326512	...	0.612359	0.588460	0.358673	0.355813	0.419359	0.424380	0.417215	0.335412	0.571060	1.000000

21 rows × 21 columns

normalized_rets = Normalized_Value.corr()
normalized_pair_value = normalized_rets.abs().unstack()
normalized_pair_value.sort_values(ascending = False)

EPAM   EPAM     1.000000
TTD    TTD      1.000000
INTC   INTC     1.000000
NVDA   NVDA     1.000000
FTNT   FTNT     1.000000
IBM    IBM      1.000000
PANW   PANW     1.000000
MA     MA       1.000000
V      V        1.000000
IAC    IAC      1.000000
ACN    ACN      1.000000
MTCH   MTCH     1.000000
ADBE   ADBE     1.000000
CRM    CRM      1.000000
NFLX   NFLX     1.000000
AMZN   AMZN     1.000000
FB     FB       1.000000
MSFT   MSFT     1.000000
CUB    CUB      1.000000
FIVN   FIVN     1.000000
GOOGL  GOOGL    1.000000
MA     V        0.892900
V      MA       0.892900
MTCH   IAC      0.786228
IAC    MTCH     0.786228
CRM    ADBE     0.785597
ADBE   CRM      0.785597
CRM    MA       0.781389
MA     CRM      0.781389
MSFT   V        0.777083
                  ...   
TTD    FIVN     0.245916
FIVN   TTD      0.245916
CUB    IBM      0.245631
IBM    CUB      0.245631
FIVN   CUB      0.244070
CUB    FIVN     0.244070
TTD    NVDA     0.230372
NVDA   TTD      0.230372
CUB    FB       0.220368
FB     CUB      0.220368
IBM    IAC      0.217917
IAC    IBM      0.217917
PANW   TTD      0.210500
TTD    PANW     0.210500
MTCH   FIVN     0.210139
FIVN   MTCH     0.210139
CUB    PANW     0.208563
PANW   CUB      0.208563
INTC   TTD      0.205115
TTD    INTC     0.205115
IBM    PANW     0.197830
PANW   IBM      0.197830
CUB    TTD      0.190216
TTD    CUB      0.190216
MTCH   IBM      0.165667
IBM    MTCH     0.165667
       FIVN     0.161164
FIVN   IBM      0.161164
TTD    IBM      0.159211
IBM    TTD      0.159211
Length: 441, dtype: float64

print("Stock returns: ")
print(rets.mean())
print('-' * 50)
print("Stock risks:")
print(rets.std())

Stock returns: 
GOOGL    0.000615
MSFT     0.001146
FB       0.000408
AMZN     0.001549
NFLX     0.001770
CRM      0.001465
ADBE     0.001733
MTCH     0.002332
IAC      0.002229
TTD      0.003777
FIVN     0.002638
V        0.001119
MA       0.001288
PANW     0.001030
IBM     -0.000521
FTNT     0.001893
NVDA     0.000956
INTC     0.000745
CUB      0.000430
ACN      0.000529
EPAM     0.001336
dtype: float64
--------------------------------------------------
Stock risks:
GOOGL    0.014273
MSFT     0.014212
FB       0.018601
AMZN     0.018599
NFLX     0.024110
CRM      0.016717
ADBE     0.018543
MTCH     0.028996
IAC      0.021549
TTD      0.043501
FIVN     0.028332
V        0.012656
MA       0.014115
PANW     0.021671
IBM      0.013002
FTNT     0.019859
NVDA     0.028336
INTC     0.016951
CUB      0.020920
ACN      0.011893
EPAM     0.016664
dtype: float64

table = pd.DataFrame()
table['Returns'] = rets.mean()
table['Risk'] = rets.std()
table.sort_values(by='Returns')

	Returns	Risk
IBM	-0.000521	0.013002
FB	0.000408	0.018601
CUB	0.000430	0.020920
ACN	0.000529	0.011893
GOOGL	0.000615	0.014273
INTC	0.000745	0.016951
NVDA	0.000956	0.028336
PANW	0.001030	0.021671
V	0.001119	0.012656
MSFT	0.001146	0.014212
MA	0.001288	0.014115
EPAM	0.001336	0.016664
CRM	0.001465	0.016717
AMZN	0.001549	0.018599
ADBE	0.001733	0.018543
NFLX	0.001770	0.024110
FTNT	0.001893	0.019859
IAC	0.002229	0.021549
MTCH	0.002332	0.028996
FIVN	0.002638	0.028332
TTD	0.003777	0.043501

table.sort_values(by='Risk')

	Returns	Risk
ACN	0.000529	0.011893
V	0.001119	0.012656
IBM	-0.000521	0.013002
MA	0.001288	0.014115
MSFT	0.001146	0.014212
GOOGL	0.000615	0.014273
EPAM	0.001336	0.016664
CRM	0.001465	0.016717
INTC	0.000745	0.016951
ADBE	0.001733	0.018543
AMZN	0.001549	0.018599
FB	0.000408	0.018601
FTNT	0.001893	0.019859
CUB	0.000430	0.020920
IAC	0.002229	0.021549
PANW	0.001030	0.021671
NFLX	0.001770	0.024110
FIVN	0.002638	0.028332
NVDA	0.000956	0.028336
MTCH	0.002332	0.028996
TTD	0.003777	0.043501

rf = 0.01
table['Sharpe Ratio'] = (table['Returns'] - rf) / table['Risk']
table

	Returns	Risk	Sharpe Ratio
GOOGL	0.000615	0.014273	-0.657515
MSFT	0.001146	0.014212	-0.623003
FB	0.000408	0.018601	-0.515678
AMZN	0.001549	0.018599	-0.454387
NFLX	0.001770	0.024110	-0.341342
CRM	0.001465	0.016717	-0.510572
ADBE	0.001733	0.018543	-0.445825
MTCH	0.002332	0.028996	-0.264458
IAC	0.002229	0.021549	-0.360636
TTD	0.003777	0.043501	-0.143054
FIVN	0.002638	0.028332	-0.259846
V	0.001119	0.012656	-0.701735
MA	0.001288	0.014115	-0.617221
PANW	0.001030	0.021671	-0.413920
IBM	-0.000521	0.013002	-0.809147
FTNT	0.001893	0.019859	-0.408216
NVDA	0.000956	0.028336	-0.319160
INTC	0.000745	0.016951	-0.546021
CUB	0.000430	0.020920	-0.457448
ACN	0.000529	0.011893	-0.796362
EPAM	0.001336	0.016664	-0.519909

table['Max Returns'] = rets.max()

table['Min Returns'] = rets.min()

table['Median Returns'] = rets.median()

total_return = stock_rets[-1:].transpose()
table['Total Return'] = 100 * total_return
table

	Returns	Risk	Sharpe Ratio	Max Returns	Min Returns	Median Returns	Total Return
GOOGL	0.000615	0.014273	-0.657515	0.064164	-0.052802	0.001230	-0.164338
MSFT	0.001146	0.014212	-0.623003	0.075705	-0.054338	0.001430	1.175420
FB	0.000408	0.018601	-0.515678	0.090613	-0.189609	0.001056	-1.584085
AMZN	0.001549	0.018599	-0.454387	0.132164	-0.078197	0.001709	1.620408
NFLX	0.001770	0.024110	-0.341342	0.135436	-0.094039	0.000892	4.522031
CRM	0.001465	0.016717	-0.510572	0.102713	-0.087061	0.001771	1.700333
ADBE	0.001733	0.018543	-0.445825	0.122418	-0.080372	0.002196	1.393806
MTCH	0.002332	0.028996	-0.264458	0.172840	-0.220925	0.002493	1.663894
IAC	0.002229	0.021549	-0.360636	0.143129	-0.177686	0.001866	1.026603
TTD	0.003777	0.043501	-0.143054	0.433909	-0.139760	0.002027	1.406729
FIVN	0.002638	0.028332	-0.259846	0.241724	-0.114168	0.001834	1.180287
V	0.001119	0.012656	-0.701735	0.069827	-0.048391	0.001905	0.763706
MA	0.001288	0.014115	-0.617221	0.067449	-0.062309	0.001788	1.337554
PANW	0.001030	0.021671	-0.413920	0.172021	-0.241540	0.000669	2.291859
IBM	-0.000521	0.013002	-0.809147	0.088645	-0.076282	0.000212	0.566223
FTNT	0.001893	0.019859	-0.408216	0.141796	-0.132991	0.002306	0.127956
NVDA	0.000956	0.028336	-0.319160	0.178259	-0.187559	0.001654	-0.112232
INTC	0.000745	0.016951	-0.546021	0.105519	-0.085890	0.000754	0.385032
CUB	0.000430	0.020920	-0.457448	0.135514	-0.117994	0.000000	0.825517
ACN	0.000529	0.011893	-0.796362	0.058967	-0.072826	0.001374	0.851080
EPAM	0.001336	0.016664	-0.519909	0.094250	-0.052893	0.001370	1.727465

table['Average Return Yearly'] = (1 + total_return)**(1 / number_of_years) - 1
table

	Returns	Risk	Sharpe Ratio	Max Returns	Min Returns	Median Returns	Total Return	Average Return Yearly
GOOGL	0.000615	0.014273	-0.657515	0.064164	-0.052802	0.001230	-0.164338	-0.000822
MSFT	0.001146	0.014212	-0.623003	0.075705	-0.054338	0.001430	1.175420	0.005860
FB	0.000408	0.018601	-0.515678	0.090613	-0.189609	0.001056	-1.584085	-0.007952
AMZN	0.001549	0.018599	-0.454387	0.132164	-0.078197	0.001709	1.620408	0.008069
NFLX	0.001770	0.024110	-0.341342	0.135436	-0.094039	0.000892	4.522031	0.022360
CRM	0.001465	0.016717	-0.510572	0.102713	-0.087061	0.001771	1.700333	0.008466
ADBE	0.001733	0.018543	-0.445825	0.122418	-0.080372	0.002196	1.393806	0.006945
MTCH	0.002332	0.028996	-0.264458	0.172840	-0.220925	0.002493	1.663894	0.008285
IAC	0.002229	0.021549	-0.360636	0.143129	-0.177686	0.001866	1.026603	0.005120
TTD	0.003777	0.043501	-0.143054	0.433909	-0.139760	0.002027	1.406729	0.007009
FIVN	0.002638	0.028332	-0.259846	0.241724	-0.114168	0.001834	1.180287	0.005884
V	0.001119	0.012656	-0.701735	0.069827	-0.048391	0.001905	0.763706	0.003811
MA	0.001288	0.014115	-0.617221	0.067449	-0.062309	0.001788	1.337554	0.006666
PANW	0.001030	0.021671	-0.413920	0.172021	-0.241540	0.000669	2.291859	0.011394
IBM	-0.000521	0.013002	-0.809147	0.088645	-0.076282	0.000212	0.566223	0.002827
FTNT	0.001893	0.019859	-0.408216	0.141796	-0.132991	0.002306	0.127956	0.000640
NVDA	0.000956	0.028336	-0.319160	0.178259	-0.187559	0.001654	-0.112232	-0.000561
INTC	0.000745	0.016951	-0.546021	0.105519	-0.085890	0.000754	0.385032	0.001923
CUB	0.000430	0.020920	-0.457448	0.135514	-0.117994	0.000000	0.825517	0.004119
ACN	0.000529	0.011893	-0.796362	0.058967	-0.072826	0.001374	0.851080	0.004246
EPAM	0.001336	0.016664	-0.519909	0.094250	-0.052893	0.001370	1.727465	0.008600

initial_value = df.iloc[0]
ending_value = df.iloc[-1]
table['CAGR'] = ((ending_value / initial_value) ** (252.0 / days)) -1
table

	Returns	Risk	Sharpe Ratio	Max Returns	Min Returns	Median Returns	Total Return	Average Return Yearly	CAGR
GOOGL	0.000615	0.014273	-0.657515	0.064164	-0.052802	0.001230	-0.164338	-0.000822	0.093233
MSFT	0.001146	0.014212	-0.623003	0.075705	-0.054338	0.001430	1.175420	0.005860	0.198988
FB	0.000408	0.018601	-0.515678	0.090613	-0.189609	0.001056	-1.584085	-0.007952	0.040634
AMZN	0.001549	0.018599	-0.454387	0.132164	-0.078197	0.001709	1.620408	0.008069	0.270015
NFLX	0.001770	0.024110	-0.341342	0.135436	-0.094039	0.000892	4.522031	0.022360	0.293159
CRM	0.001465	0.016717	-0.510572	0.102713	-0.087061	0.001771	1.700333	0.008466	0.258622
ADBE	0.001733	0.018543	-0.445825	0.122418	-0.080372	0.002196	1.393806	0.006945	0.311459
MTCH	0.002332	0.028996	-0.264458	0.172840	-0.220925	0.002493	1.663894	0.008285	0.391361
IAC	0.002229	0.021549	-0.360636	0.143129	-0.177686	0.001866	1.026603	0.005120	0.413542
TTD	0.003777	0.043501	-0.143054	0.433909	-0.139760	0.002027	1.406729	0.007009	0.659274
FIVN	0.002638	0.028332	-0.259846	0.241724	-0.114168	0.001834	1.180287	0.005884	0.477057
V	0.001119	0.012656	-0.701735	0.069827	-0.048391	0.001905	0.763706	0.003811	0.197632
MA	0.001288	0.014115	-0.617221	0.067449	-0.062309	0.001788	1.337554	0.006666	0.229073
PANW	0.001030	0.021671	-0.413920	0.172021	-0.241540	0.000669	2.291859	0.011394	0.146571
IBM	-0.000521	0.013002	-0.809147	0.088645	-0.076282	0.000212	0.566223	0.002827	-0.099870
FTNT	0.001893	0.019859	-0.408216	0.141796	-0.132991	0.002306	0.127956	0.000640	0.342372
NVDA	0.000956	0.028336	-0.319160	0.178259	-0.187559	0.001654	-0.112232	-0.000561	0.100283
INTC	0.000745	0.016951	-0.546021	0.105519	-0.085890	0.000754	0.385032	0.001923	0.110117
CUB	0.000430	0.020920	-0.457448	0.135514	-0.117994	0.000000	0.825517	0.004119	0.037490
ACN	0.000529	0.011893	-0.796362	0.058967	-0.072826	0.001374	0.851080	0.004246	0.082661
EPAM	0.001336	0.016664	-0.519909	0.094250	-0.052893	0.001370	1.727465	0.008600	0.231237

table.sort_values(by='Average Return Yearly')

	Returns	Risk	Sharpe Ratio	Max Returns	Min Returns	Median Returns	Total Return	Average Return Yearly	CAGR
FB	0.000408	0.018601	-0.515678	0.090613	-0.189609	0.001056	-1.584085	-0.007952	0.040634
GOOGL	0.000615	0.014273	-0.657515	0.064164	-0.052802	0.001230	-0.164338	-0.000822	0.093233
NVDA	0.000956	0.028336	-0.319160	0.178259	-0.187559	0.001654	-0.112232	-0.000561	0.100283
FTNT	0.001893	0.019859	-0.408216	0.141796	-0.132991	0.002306	0.127956	0.000640	0.342372
INTC	0.000745	0.016951	-0.546021	0.105519	-0.085890	0.000754	0.385032	0.001923	0.110117
IBM	-0.000521	0.013002	-0.809147	0.088645	-0.076282	0.000212	0.566223	0.002827	-0.099870
V	0.001119	0.012656	-0.701735	0.069827	-0.048391	0.001905	0.763706	0.003811	0.197632
CUB	0.000430	0.020920	-0.457448	0.135514	-0.117994	0.000000	0.825517	0.004119	0.037490
ACN	0.000529	0.011893	-0.796362	0.058967	-0.072826	0.001374	0.851080	0.004246	0.082661
IAC	0.002229	0.021549	-0.360636	0.143129	-0.177686	0.001866	1.026603	0.005120	0.413542
MSFT	0.001146	0.014212	-0.623003	0.075705	-0.054338	0.001430	1.175420	0.005860	0.198988
FIVN	0.002638	0.028332	-0.259846	0.241724	-0.114168	0.001834	1.180287	0.005884	0.477057
MA	0.001288	0.014115	-0.617221	0.067449	-0.062309	0.001788	1.337554	0.006666	0.229073
ADBE	0.001733	0.018543	-0.445825	0.122418	-0.080372	0.002196	1.393806	0.006945	0.311459
TTD	0.003777	0.043501	-0.143054	0.433909	-0.139760	0.002027	1.406729	0.007009	0.659274
AMZN	0.001549	0.018599	-0.454387	0.132164	-0.078197	0.001709	1.620408	0.008069	0.270015
MTCH	0.002332	0.028996	-0.264458	0.172840	-0.220925	0.002493	1.663894	0.008285	0.391361
CRM	0.001465	0.016717	-0.510572	0.102713	-0.087061	0.001771	1.700333	0.008466	0.258622
EPAM	0.001336	0.016664	-0.519909	0.094250	-0.052893	0.001370	1.727465	0.008600	0.231237
PANW	0.001030	0.021671	-0.413920	0.172021	-0.241540	0.000669	2.291859	0.011394	0.146571
NFLX	0.001770	0.024110	-0.341342	0.135436	-0.094039	0.000892	4.522031	0.022360	0.293159